检索结果-内蒙古大学图书馆

Proceedings of the 2023 7th International Conference on Advances in image processing

作者： Zoltan Domokos Laszlo G. Varga Department of Image Processing and Computer Graphics University of Szeged Hungary

ISBN: (纸本)9798400708275

In computed tomography and several related scientific domains, the Fourier slice theorem is a powerful mathematical tool to solve the problem of image reconstruction. Although this theorem is well understood in the continuous case, a detailed quantitative analysis of artifacts caused by discretization is rarely found in the computed tomographic literature. Assuming a practical Fourier Domain Reconstruction (FDR) algorithm, which performs resampling by interpolation or approximation in the frequency domain, artifacts have two main sources. One of these is a combination of truncation and aliasing, introduced by Discrete Fourier Transform (DFT), while the other is the numerical error of the function estimation algorithm that performs resampling. Here, we provide an algebraic method to quantitatively isolate distinct sources of error and construct a set of novel metrics that can be used in the numerical analysis of reconstruction methods.

关键词： computed tomography fourier domain reconstruction interpolation neural networks

来源：评论

学校读者我要写书评

暂无评论

Gesture-based computer mouse using Kinect sensor

Gesture-based computer mouse using Kinect sensor

引用

International Conference on Cognitive Infocommunications (CogInfoCom)

作者： Szilvia Szeghalmy Marianna Zichar Attila Fazekas Department of Computer Graphics and Image Processing University of Debrecen Debrecen

This paper introduces a vision-based gesture mouse system, which is roughly independent from the lighting conditions, because it only uses the depth data for hand sign recognition. A Kinect sensor was used to develop the system, but other depth sensing cameras are adequate as well, if their resolutions are similar or better than the resolution of Kinect sensor. Our aim was to find a comfortable, user-friendly solution, which can be used for a long time without getting tired. The implementation of the system was developed in C++, and two types of test were performed too. We investigated how fast the user can position with the cursor and click on objects and we also examined which controls of the graphical user interfaces (GUI) are easy to use and which ones are difficult to use with our gesture mouse. Our system is precise enough to use efficiently most of the elements of traditional GUI such as buttons, icons, scrollbars, etc. The accuracy achieved by advanced users is only slightly below as if they used the traditional mouse.

关键词： Mice Indexes computers Graphical user interfaces Thumb Conferences Accuracy

来源：评论

学校读者我要写书评

暂无评论

Car recognition from frontal images in mobile environment

Car recognition from frontal images in mobile environment

引用

International Symposium on image and Signal processing and Analysis

作者： Viktor Varjas Attila Tanács Department of Image Processing and Computer Graphics University of Szeged Hungary

Recognition of car make and model from frontal images is a common problem in computer vision. We refined existing approaches based on ROIs defined relative to the number plate. Square-Mapped-Gradient features are extracted from the ROI and recognition is accomplished by classification utilizing a learning set. The classifier is evaluated using ground truth data provided manually. Via numerical simulations we evaluated the detection tolerance of the method and proposed semi-automatic and fully automatic methods. The SMG-based classification is able to give nearly perfect results when there is no outlier class, which decreases to 92% and 87% in case of the semi-automatic and fully automatic methods, respectively. Separation between outliers and known types can be balanced by a threshold. Since the size of the learning set can be kept low and the size of the SMG features are small, this approach can be successfully used to solve mobile client-server scenarios.

关键词： Vectors Training image recognition Feature extraction Databases Mathematical model Mobile communication

来源：评论

学校读者我要写书评

暂无评论

Comfortable mouse control using 3D depth sensor

Comfortable mouse control using 3D depth sensor

引用

International Conference on Cognitive Infocommunications (CogInfoCom)

作者： Szilvia Szeghalmy Marianna Zichar Attila Fazekas Department of Computer Graphics and Image Processing University of Debrecen Debrecen

We have been developing a hand gesture based computer mouse controlling system, whose central issue is the precise controllability and the comfort of the user. The Kinect for Windows sensor provides the data to process. We have investigated 11 different hand signs inside a special zone to choose appropriate gestures for controlling. In this paper we point out the advantages and disadvantages of the potential solutions and present the preliminary results of our system.

关键词： Mice Thumb computers Three-dimensional displays Indexes Feature extraction Elbow

来源：评论

学校读者我要写书评

暂无评论

Fast Linear Registration of 3D Objects Segmented from Medical images

Fast Linear Registration of 3D Objects Segmented from Medica...

引用

2011 4th International Conference on Biomedical Engineering and Informatics(第四届生物医学工程与信息学国际会议 BMEI 2011)

作者： Attila Tanacs Zoltan Kato Department of Image Processing and Computer Graphics University of Szeged Hungary

In this paper a linear registration framework is used for medical image registration using segmented binary objects. The method is best suited for problems where the segmentation is available, but we also propose a general bone segmentation approach for CT images. We focus on the case when the objects to be registered differ considerably because of segmentation errors. We check the applicability of the method to bone segmentation of pelvic and thoracic CT images. Comparison is also made against a classical mutual information-based registration method.

关键词： Computed tomography image segmentation Bones Equations Biomedical imaging Three dimensional displays Mathematical model

来源：评论

学校读者我要写书评

暂无评论

A redundancy removal method for bill images

引用

Journal of computers 2011年第1期22卷 9-17页

作者： Li, Li Li, Fangfang Lu, Jian-Feng Department of Computer Graphics and Image Processing Hangzhou Dianzi University Hangzhou 310000 China

The digitalization processes of bills produce frequently digital images with a mass of redundant background caused by rotation angles and misoperations in the scanning process. The redundant background occupies much storage space. First, this paper proposes a method that combines Hough transform and mathematical morphology to detect the skew. Secondly, the redundant background of bill images is removed after recognizing the coordinates of the top-left and bottom-right points of the target area. Last, experimental results are given on different types of bill images. The method provided in this paper is automated and simple to implement.

关键词： Mathematical morphology

来源：评论

学校读者我要写书评

暂无评论

Localization of visual codes in the DCT domain using deep rectifier neural networks

Localization of visual codes in the DCT domain using deep re...

引用

International Workshop on Artificial Neural Networks and Intelligent Information processing, ANNIIP 2014 - In Conjuction with the International Conference on Informatics in Control, Automation and Robotics, ICINCO 2014

作者： Bodnár, Péter Grósz, Tamás Tóth, László Nyúl, László G. University of Szeged Department of Image Processing and Computer Graphics Szeged Hungary MTA-SZTE Research Group on Artificial Intelligence Hungarian Academy of Sciences University of Szeged Szeged Hungary

ISBN: (纸本)9789897580413

The reading process of visual codes consists of two steps, localization and data decoding. This paper presents a novel method for QR code localization using deep rectifier neural networks, trained directly in the JPEG DCT domain, thus making image decompression unnecessary. This approach is efficient with respect to both storage and computation cost, being convenient, since camera hardware can provide JPEG stream as their output in many cases. The structure of the neural networks, regularization, and training data parameters, like input vector length and compression level, are evaluated and discussed. The proposed approach is not exclusively for QR codes, but can be adapted to Data Matrix codes or other two-dimensional code types as well.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Topologically Robust B-spline Reconstruction of Fibers from 3D images 8th

Topologically Robust B-spline Reconstruction of Fibers from ...

引用

8th Workshop on Topological Methods in Data Analysis and Visualization, TopoInVis 2019

作者： Mosbach, Dennis Schladitz, Katja Hamann, Bernd Hagen, Hans Computer Graphics and HCI Group University of Kaiserslautern Kaiserslautern67663 Germany Image Processing Department Fraunhofer ITWM Kaiserslautern67663 Germany Department of Computer Science University of California DavisCA95616 United States

ISBN: (纸本)9783030834999

The micro-structure of wood-based insulation materials is analyzed to gain insight into how features on microscopic scales influence macroscopic thermal conductivity. Three-dimensional (3D) image data obtained by micro-computed tomography reveals a complex structure formed by cellulose fibers. To study the effect of geometry changes, simple B-spline representations of these fibers are highly desirable. A straightforward solution is to extract a triangulated isosurface from the 3D image and partition it into quadrilateral macro-cells with disk-like topology. For each cell, a B-spline surface is constructed by minimizing a least squares error term. However, the physical processing of the material affects the structure of the fibers. The resulting changes in surface topology cause difficulties for the quadrilateral partitioning. image processing tools can solve these topological issues, but they also impact geometry. We present a novel approach that splits geometry and topology processing of the data. It allows for topological simplification while still preserving the geometry of a scanned object. Established B-spline approximation methods are used to create a model. The involved mathematical equations are described in detail with a focus on simple implementation. Our presented results demonstrate that smooth and accurate models can be created for challenging data. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Fibers

来源：评论

学校读者我要写书评

暂无评论

A new rectangular partitioning based lossless binary image compression scheme

A new rectangular partitioning based lossless binary image c...

引用

Canadian Conference on Electrical and computer Engineering 2005

作者： Zahir, Saif Naqvi, Mehmood Image Processing Graphics and Multimedia Lab. Department of Computer Science UNBC Prince George BC V2N 4Z9 Canada

In this paper, we propose a lossless binary image compression scheme that can achieve high compression ratio via partitioning the black regions (one's) of the input image into rectangles. After partitioning, the top-left and the bottom-right vertices of each rectangle are identified and the coordinates of which are efficiently coded. Three different routines are used in this research. The proposed scheme is targeting images, which contain graphs and tables with solid gridlines in the background on the one hand. While on the other hand it is suitable for text images of languages where many characters have dots "nuqta" on them such as Urdu, Persian, and Arabic with big fonts. The proposed scheme has outperformed CCITT run length coding, modified READ, and REC significantly. Also it is faster and simpler to implement than the method reported in reference [6]. © 2005 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

A fast pavement location approach for autonomous car navigation 19

引用

19th Iberoamerican Congress on Pattern Recognition, CIARP 2014

作者： Rateke, Thiago Justen, Karla A. Chiarella, Vito F. Linhares, Rodrigo T. F. Sobieranski, Antonio Carlos Comunello, Eros von Wangenheim, Aldo Federal University of Santa Catarina Brazil Laboratory of Image Processing and Computer Graphics National Brazilian Institute for Digital Convergence Brazil Federal University of Parana Department of Informatics Brazil

ISBN: (纸本)9783319125671

This paper describes a fast image segmentation approach designed for pavement detection in a moving camera. The method is based on a graph-oriented segmentation approach where gradient information is used temporally as a system of discontinuities to control merging between adjacent regions. The method presumes that the navigable path usually is located at specific positions on the scene, and a predefined set of seed points is used to locate the region of interest. The obtained results shown the proposed approach is able to accurately detect in an inexpensive computation manner the navigable path even in non-optimum scenarios such as miss-painted or unpaved dirt roads. Validation was conducted using a dataset with 701 samples of navigable paths, presenting a very high precision for real-time applications. © Springer International Publishing Switzerland 2014.

关键词： Pavements

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：